© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19683
    Prev
    Next
    INDEX
    Explanations

    sentences indicating the speaker's identity or state of being

    oai_token-act-pair · gpt-3.5-turbo

    the assertion of personal identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.69
     Awakens
    -0.67
    Tang
    -0.66
     Durham
    -0.66
     Tactics
    -0.66
     Moons
    -0.65
    pedia
    -0.65
    ":""},{"
    -0.64
     Rohing
    -0.63
     Dough
    -0.63
    POSITIVE LOGITS
    sterdam
    1.05
    ethyst
    0.97
    ajor
    0.96
    ateurs
    0.94
    azon
    0.93
    essage
    0.88
     am
    0.86
    oen
    0.85
    oval
    0.83
    abella
    0.81
    Activations Density 0.021%

    No Known Activations